Skip to content

Benchmark

Irish-BLiMP accuracy (5-shot; §5.3)

Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.

Models and systems measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

74.9%
Mean
81.1%
Median
6.2%
Std dev
68.7%
10th percentile
81.1%
90th percentile
68.7%
Min
68.7%81.1%
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
gpt-5prompting: 5-shot, context: §5.3, source: prose· Irish-BLiMP (arXiv:2510.20957v1) data81.1%
Llama-4-Scout-17B-16E-Instr.prompting: 5-shot, context: §5.3, source: prose· Irish-BLiMP (arXiv:2510.20957v1) data68.7%

Data credits: Josh McGiff, Khanh-Tung Tran, William Mulcahy, Dáibhidh Ó Luinín, Jake Dalzell, Róisín Ní Bhroin, Adam Burke, Barry O'Sullivan, Hoang D. Nguyen and Nikola S. Nikolov. Irish-BLiMP, arXiv:2510.20957v1, submitted 2025-10-23. CC BY 4.0 article numeric/protocol extract; restructured, printed values unchanged. No task, prompt or model rights asserted. (licence)